Artificial Intelligence, Physics-Informed Machine Learning, and Data-Driven Digital Twins for Renewable Energy Forecasting, Optimization, and Smart Energy Systems

Submission Deadline: 01 June 2027 View: 105 Submit to Special Issue

Guest Editor(s)

Dr. Omer A. Alawi

Email: omeralawi@utm.my

Affiliation: Department of Thermofluids, School of Mechanical Engineering, Universiti Teknologi Malaysia, 81310, UTM Skudai, Johor Bahru, Malaysia

Homepage:

Research Interests: AI & machine learning for energy systems, renewable energy forecasting, physics-informed machine learning, smart grids & energy management, energy storage & battery analytics

Dr. Ismail Masalha

Email: masalha@bau.edu.jo

Affiliation: Department of Mechanical Engineering, Faculty of Engineering Technology, Al-Balqa Applied University, Amman, Jordan

Homepage:

Research Interests: renewable energy systems, photovoltaic technologies, heat transfer, fluid flow, computational fluid dynamics (CFD), porous media, nanofluids, numerical modeling, application of artificial intelligence, machine learning

Summary

The rapid expansion of renewable energy systems has introduced new challenges related to variability, uncertainty, and operational complexity. Accurate forecasting and intelligent optimization are essential to improving the reliability, efficiency, and economic viability of renewable energy technologies. Recent advances in machine learning (ML), deep learning (DL), artificial intelligence (AI), and data-driven analytics have created unprecedented opportunities to improve prediction, control, planning, and decision-making for renewable energy.

This Special Issue aims to gather high-quality research contributions that explore innovative machine learning and data-driven methodologies for renewable energy forecasting and optimization. Topics of interest include, but are not limited to, solar irradiance and photovoltaic power forecasting, wind speed and wind power prediction, electricity demand and price forecasting, hybrid renewable energy systems, energy storage management, smart grids, and AI-enabled energy optimization. Contributions addressing explainable AI, uncertainty quantification, digital twins, physics-informed machine learning, big-data analytics, and real-time energy management are particularly encouraged.

The Special Issue seeks original research articles, review papers, and case studies that demonstrate methodological advances and practical applications across renewable energy systems. By bringing together researchers, engineers, and practitioners, this collection aims to highlight emerging trends and foster the development of intelligent, resilient, and sustainable energy solutions for future energy systems.

Suggested themes include:
· Solar Irradiance and Photovoltaic Power Forecasting
· Wind Speed and Wind Power Prediction
· Electricity Demand, Load, and Price Forecasting
· Deep Learning and Transformer-Based Forecasting Models
· Explainable Artificial Intelligence (XAI) in Energy Systems
· Physics-Informed Machine Learning for Energy Applications
· Smart Grids and Intelligent Energy Management
· Energy Storage Optimization and Battery Analytics
· Digital Twins for Renewable Energy Systems
· Uncertainty Quantification and Probabilistic Forecasting
· Generative AI for Energy Applications
· Large Language Models (LLMs) in Energy Systems
· AI for Hydrogen Energy Systems
· Federated Learning for Smart Grids
· Edge AI and IoT-Based Energy Management
· AI for Building Energy Prediction and Optimization
· Reinforcement Learning for Renewable Energy Control
· Explainable Physics-Informed Neural Networks
· Hybrid CFD–AI Models for Thermal Systems
· AI-Driven Fault Detection in Renewable Energy Systems

Keywords